© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10785
    Prev
    Next
    INDEX
    Explanations

    genetic terms and mutations related to medical research

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.21
    0.7%
    1499
    +0.10
    0.3%
    283
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.21
    0.05
    876
    +0.10
    -0.01
    194
    +0.09
    0.02
    Negative Logits
    Бележки
    -0.55
     Juventud
    -0.53
    Jîn
    -0.52
     accueille
    -0.52
    racked
    -0.52
    WindowConstants
    -0.52
    المشاركات
    -0.52
     Factbook
    -0.52
     Krzysz
    -0.51
     dépasse
    -0.51
    POSITIVE LOGITS
     effe
    1.48
     aen
    1.36
     fup
    1.33
     waer
    1.28
     ftu
    1.25
     poff
    1.25
     desir
    1.23
     paff
    1.23
     „,
    1.22
     thut
    1.21
    Activations Density 0.210%

    No Known Activations